Skip to main content

Poe

Aggregator

Poe routes one API key to many upstream providers, so you can switch models without new accounts.

Visit poe.com
Models104
Cheapest for
2 models
Serves
3 model types
Visits in September 20265.4M−1.9%Unique visitors 1.4M
  1. Apr
  2. May
  3. Jun
  4. Jul
  5. Aug
  6. Sep
Models by type

Models on Poe

ModelInputOutputvs officialContext
Qwen3.7 Flash$0.03/1M$0.131/1M
from $0.091 at APIMart
+19%1M
Seed 2.1 Turbo$0.636/1M$3.16/1M
from $1.67 at CometAPI
+26%256K
Step 3.7 Flash$0.202/1M$1.16/1M
from $0.925 at APIMart
+26%262K
Step 5 Preview$1.01/1M$2.73/1M
from $2.70 at Deep Infra
+1%1.02M

Poe at a glance

104 models in total: 98 text, 5 image, 1 video. The cheapest is Qwen3.5 4B at $0.071 /1M. OpenAI GPT-5.4 has the largest context window, 1.05M tokens. The most searched is Kimi K3, with about 658K Google searches a month. The newest is Kimi K3.1 Pro Highspeed, released Oct 23, 2026.

Cheapest

  1. Qwen3.5 4B$0.071/1M
  2. Qwen3.5 9B$0.131/1M
  3. Qwen3.7 Flash$0.131/1M
  4. GPT OSS 20B$0.141/1M
  5. Ling 3.0 Flash Fin$0.182/1M

Largest context

  1. OpenAI GPT-5.41.05M
  2. OpenAI GPT-5.4 Pro1.05M
  3. Kimi K31.05M
  4. Muse Wonder1.05M
  5. GLM-5.31.05M

Most searched

  1. Kimi K3658K
  2. Muse Wonder569K
  3. Nano Banana Pro Preview478K
  4. GLM-5.3276K
  5. Nano Banana 2.1251K

Newest

  1. Kimi K3.1 Pro HighspeedOct 23, 2026
  2. Mercury 3Oct 19, 2026
  3. DeepSeek V4 Flash Vision ExpOct 17, 2026
  4. Muse Spark OpenOct 15, 2026
  5. Muse WonderOct 12, 2026